Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A conversation processing method based on artificial intelligence, wherein the method comprises: obtaining user feedback information provided by conversation service conducted by a user and a model conversation understanding system; according to the user feedback information, performing adjustment processing for a service state of the model conversation understanding system, to obtain an adjustment state of the model conversation understanding system; and using the model conversation understanding system to execute the conversation service based on the adjustment state of the model conversation understanding system, wherein the user feedback information comprises active feedback information and passive feedback information, the active feedback information comprising a newly-added intent, parameter, execution action and a triggering rule of the execution action; and wherein before obtaining user feedback information provided by conversation service conducted by a user and a model conversation understanding system, the method further comprises: obtaining training feedback information provided by conversation service conducted by a user and a basic conversation understanding system; according to the training feedback information, performing adjustment processing for a service state of the basic conversation understanding system, to obtain an adjustment state of the basic conversation understanding system; and performing data merging processing according to the training feedback information and the adjustment state of the basic conversation understanding system, to obtain model training data for building the model conversation understanding system, wherein the adjustment processing for a service state of the basic conversation understanding system comprises: for the active feedback information, correction of a speech recognition result; correction of an intent recognition result; correction or supplement of parameter types and parameter values; correction or supplement of an execution result; confirmation or negation of a speech recognition result; an intent recognition result, parameters and an execution result; and a certain newly-added intent, parameter, execution action and a triggering rule of the execution action; and for the passive feedback information, a query for the speech recognition result; a query for the intent recognition result; a query for the parameter type or parameter value; a query for the execution result; and a query for missing data.
2. The method according to claim 1 , wherein the user feedback information comprises at least one of the following information: positive information; negative information; error-correcting information; clarifying information; and defining information.
This invention relates to systems and methods for processing user feedback in interactive applications, particularly to improve the accuracy and relevance of responses generated by artificial intelligence (AI) or automated systems. The problem addressed is the need for AI systems to effectively interpret and utilize diverse types of user feedback to enhance performance, correct errors, and refine responses. The method involves collecting user feedback in various forms, including positive feedback (e.g., approval or satisfaction), negative feedback (e.g., disapproval or dissatisfaction), error-correcting information (e.g., corrections to mistakes), clarifying information (e.g., requests for further explanation), and defining information (e.g., definitions or context for ambiguous terms). The feedback is analyzed to identify patterns, errors, or areas for improvement, which are then used to update the system's knowledge base, algorithms, or response generation logic. This ensures that future interactions are more accurate, relevant, and aligned with user expectations. The method may be applied in chatbots, virtual assistants, recommendation systems, or other AI-driven applications where user interaction is critical. By systematically categorizing and processing different types of feedback, the system can dynamically adapt to user needs, reducing errors and improving overall user experience. The approach enhances the system's ability to learn from interactions, making it more effective over time.
3. The method according to claim 1 , wherein before obtaining training feedback information provided by conversation service conducted by a user and a basic conversation understanding system, the method further comprises: obtaining application scenario information of a conversation service scenario provided by a developer, the application scenario information including intent information, parameter information and corresponding execution actions; according to the application scenario information, building the basic conversation understanding system having basic service logic.
4. The method according to claim 1 , wherein after obtaining training feedback information provided by conversation service conducted by a user and a basic conversation understanding system, the method further comprises: obtaining evaluation data of the basic conversation understanding system according to the training feedback information; obtaining a satisfaction degree index of the basic conversation understanding system according to the evaluation data.
5. The method according to claim 1 , wherein after the step of, according to the user feedback information, performing adjustment processing for a service state of the model conversation understanding system, to obtain an adjustment state of the model conversation understanding system, the method further comprises: performing data merging processing according to the user feedback information and the adjustment state of the model conversation understanding system, to obtain updated training data for updating the model conversation understanding system.
6. A device, wherein the device comprises: one or more processors; a memory for storing one or more programs, the one or more programs, when executed by said one or more processors, enable said one or more processors to implement a conversation processing method based on artificial intelligence, wherein the method comprises: obtaining user feedback information provided by conversation service conducted by a user and a model conversation understanding system; according to the user feedback information, performing adjustment processing for a service state of the model conversation understanding system, to obtain an adjustment state of the model conversation understanding system; and using the model conversation understanding system to execute the conversation service based on the adjustment state of the model conversation understanding system, wherein the user feedback information comprises active feedback information and passive feedback information, the active feedback information comprising a newly-added intent, parameter, execution action and a triggering rule of the execution action; and wherein before obtaining user feedback information provided by conversation service conducted by a user and a model conversation understanding system, the method further comprises: obtaining training feedback information provided by conversation service conducted by a user and a basic conversation understanding system; according to the training feedback information, performing adjustment processing for a service state of the basic conversation understanding system, to obtain an adjustment state of the basic conversation understanding system; and performing data merging processing according to the training feedback information and the adjustment state of the basic conversation understanding system, to obtain model training data for building the model conversation understanding system, wherein the adjustment processing for a service state of the basic conversation understanding system comprises. for the active feedback information, correction of a speech recognition result; correction of an intent recognition result; correction or supplement of parameter types and parameter values; correction or supplement of an execution result; confirmation or negation of a speech recognition result; an intent recognition result, parameters and an execution result; and a certain newly-added intent, parameter, execution action and a triggering rule of the execution action; and for the passive feedback information, a query for the speech recognition result; a query for the intent recognition result; a query for the parameter type or parameter value; a query for the execution result; and a query for missing data.
7. The device according to claim 6 , wherein the user feedback information comprises at least one of the following information: positive information; negative information; error-correcting information; clarifying information; and defining information.
8. The device according to claim 6 , wherein before obtaining training feedback information provided by conversation service conducted by a user and a basic conversation understanding system, the method further comprises: obtaining application scenario information of a conversation service scenario provided by a developer, the application scenario information including intent information, parameter information and corresponding execution actions; according to the application scenario information, building the basic conversation understanding system having basic service logic.
9. The device according to claim 6 , wherein after obtaining training feedback information provided by conversation service conducted by a user and a basic conversation understanding system, the method further comprises: obtaining evaluation data of the basic conversation understanding system according to the training feedback information; obtaining a satisfaction degree index of the basic conversation understanding system according to the evaluation data.
This invention relates to improving the performance of a basic conversation understanding system used in automated conversation services. The system processes user interactions and generates responses, but its accuracy and effectiveness can be limited. The invention addresses this by implementing a feedback mechanism to evaluate and enhance the system's performance. The device includes a basic conversation understanding system that conducts conversations with users. After each interaction, training feedback information is collected, which reflects the quality and accuracy of the system's responses. This feedback is used to generate evaluation data, which quantifies the system's performance. The evaluation data is then processed to determine a satisfaction degree index, representing how well the system meets user expectations. The satisfaction degree index is derived from analyzing the training feedback information, which may include user ratings, error logs, or other performance metrics. By continuously monitoring and updating this index, the system can identify areas for improvement and refine its conversation algorithms. This iterative feedback loop ensures that the basic conversation understanding system becomes more accurate and user-friendly over time. The invention enhances automated conversation services by providing a structured way to assess and improve the system's performance based on real-world interactions. This leads to better user experiences and more effective automated conversation systems.
10. The device according to claim 6 , wherein after the step of, according to the user feedback information, performing adjustment processing for a service state of the model conversation understanding system, to obtain an adjustment state of the model conversation understanding system, the method further comprises: performing data merging processing according to the user feedback information and the adjustment state of the model conversation understanding system, to obtain updated training data for updating the model conversation understanding system.
This invention relates to a model conversation understanding system that improves its performance based on user feedback. The system processes user feedback to adjust its service state, such as modifying conversation parameters or response strategies, to better align with user expectations. After adjusting the system's state, the invention further enhances the system by merging the user feedback with the adjusted state to generate updated training data. This training data is then used to refine the model, ensuring continuous improvement in conversation accuracy and relevance. The approach ensures that the system dynamically adapts to user interactions, reducing errors and enhancing user satisfaction over time. The invention is particularly useful in applications like virtual assistants, chatbots, and automated customer service systems where real-time feedback-driven learning is critical. By integrating feedback into both immediate adjustments and long-term training, the system achieves a balance between short-term responsiveness and long-term accuracy improvements. The method ensures that the model remains up-to-date with evolving user preferences and interaction patterns, making it more effective in real-world deployment scenarios.
11. A non-transitory computer readable storage medium on which a computer program is stored, wherein the program, when executed by a processor, implements a conversation processing method based on artificial intelligence, wherein the method comprises: obtaining user feedback information provided by conversation service conducted by a user and a model conversation understanding system; according to the user feedback information, performing adjustment processing for a service state of the model conversation understanding system, to obtain an adjustment state of the model conversation understanding system; and using the model conversation understanding system to execute the conversation service based on the adjustment state of the model conversation understanding system, wherein the user feedback information comprises active feedback information and passive feedback information, the active feedback information comprising a newly-added intent, parameter, execution action and a triggering rule of the execution action; and wherein before obtaining user feedback information provided by conversation service conducted by a user and a model conversation understanding system, the method further comprises: obtaining training feedback information provided by conversation service conducted by a user and a basic conversation understanding system; according to the training feedback information, performing adjustment processing for a service state of the basic conversation understanding system, to obtain an adjustment state of the basic conversation understanding system; and performing data merging processing according to the training feedback information and the adjustment state of the basic conversation understanding system, to obtain model training data for building the model conversation understanding system, wherein the adjustment processing for a service state of the basic conversation understanding system comprises: for the active feedback information, correction of a speech recognition result; correction of an intent recognition result; correction or supplement of parameter types and parameter values; correction or supplement of an execution result; confirmation or negation of a speech recognition result; an intent recognition result, parameters and an execution result; and a certain newly-added intent, parameter, execution action and a triggering rule of the execution action; and for the passive feedback information, a query for the speech recognition result; a query for the intent recognition result; a query for the parameter type or parameter value; a query for the execution result; and a query for missing data.
12. The non-transitory computer readable storage medium according to claim 11 , wherein the user feedback information comprises at least one of the following information: positive information; negative information; error-correcting information; clarifying information; and defining information.
13. The non-transitory computer readable storage medium according to claim 11 , wherein before obtaining training feedback information provided by conversation service conducted by a user and a basic conversation understanding system, the method further comprises: obtaining application scenario information of a conversation service scenario provided by a developer, the application scenario information including intent information, parameter information and corresponding execution actions; according to the application scenario information, building the basic conversation understanding system having basic service logic.
14. The non-transitory computer readable storage medium according to claim 11 , wherein after obtaining training feedback information provided by conversation service conducted by a user and a basic conversation understanding system, the method further comprises: obtaining evaluation data of the basic conversation understanding system according to the training feedback information; obtaining a satisfaction degree index of the basic conversation understanding system according to the evaluation data.
15. The non-transitory computer readable storage medium according to claim 11 , wherein after the step of, according to the user feedback information, performing adjustment processing for a service state of the model conversation understanding system, to obtain an adjustment state of the model conversation understanding system, the method further comprises: performing data merging processing according to the user feedback information and the adjustment state of the model conversation understanding system, to obtain updated training data for updating the model conversation understanding system.
Unknown
April 13, 2021
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.